{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:06:53Z","timestamp":1768453613913,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076259"],"award-info":[{"award-number":["62076259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental and Applicational Research Funds of Guangdong province","award":["2023A1515012946"],"award-info":[{"award-number":["2023A1515012946"]}]},{"name":"Fundamental Research Funds for the Central Universities-Sun Yat-sen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tkde.2024.3523472","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:31:49Z","timestamp":1735327909000},"page":"1241-1254","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Multi-Agent Meta-Reinforcement Learning for Cross-Channel Bidding"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9469-0051","authenticated-orcid":false,"given":"Shenghong","family":"He","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-3663","authenticated-orcid":false,"given":"Chao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3247-0483","authenticated-orcid":false,"given":"Shangqin","family":"Mao","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7129-0250","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianlong","family":"Xie","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.1100.0583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/00222437211030201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2501040.2501980"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3251897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3151618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282907"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22163"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/15567036.2023.2165740"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498373"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3343111"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339655"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919450"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3606274.3606281"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.10.021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187888"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"key":"ref24","article-title":"Offline reinforcement learning: Tutorial, review","author":"Levine","year":"2020"},{"key":"ref25","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref26","first-page":"11761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref27","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref28","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref29","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019"},{"key":"ref30","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref31","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref32","article-title":"AlgaeDICE: Policy gradient from arbitrary experience","author":"Nachum","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref34","first-page":"1529","article-title":"Dice: The infinitely differentiable Monte-Carlo estimator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref35","first-page":"5405","article-title":"Evolved policy gradients","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref36","first-page":"1","article-title":"Varibad: A very good method for Bayes-adaptive deep RL via meta-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zintgraf"},{"key":"ref37","first-page":"1","article-title":"Meta-Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fakoor"},{"key":"ref38","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref39","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"issue":"1","key":"ref41","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110043"},{"key":"ref43","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov"},{"key":"ref44","first-page":"1","article-title":"Offline reinforcement learning with value-based episodic memory","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29680"},{"key":"ref47","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref48","first-page":"17221","article-title":"Plan better amid conservatism: Offline multi-agent reinforcement learning with actor rectification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pan"},{"key":"ref49","first-page":"52413","article-title":"Offline multi-agent reinforcement learning with implicit global-to-local value regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref50","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref53","article-title":"Mildly conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lyu"},{"key":"ref54","first-page":"1","article-title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ajay"},{"key":"ref55","first-page":"20410","article-title":"Bcorle(): An offline reinforcement learning and evaluation framework for coupons allocation in e-commerce market","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref56","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29658"},{"key":"ref58","first-page":"25747","article-title":"Robust task representations for offline meta-reinforcement learning via contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan"},{"key":"ref59","first-page":"80024","article-title":"Context shift reduction for offline meta-reinforce ment learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref60","first-page":"833","article-title":"Stochastic neighbor embedding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hinton"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/10855162\/10817487.pdf?arnumber=10817487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:50:35Z","timestamp":1738090235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3523472","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}